kostiantynk commited on
Commit
27ed65e
·
verified ·
1 Parent(s): aab66bf

Training in progress, step 9, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f63ca9da7918a3e16d8b626bdb0617bf3d8dcbf787f66686e0b429f299311c93
3
  size 104902272
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:279cf1a7b03547849a22044651137f8d455db649cb3e5670256f077e6295c909
3
  size 104902272
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7dcdceb7b9d1b866d033e11f1c6b099f55549f647de04870c6c3e867364d851d
3
  size 53622996
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a0d684b53d7c3cc99870e4a5a610dc5352d4637f79c70641b4a08f0e292239f
3
  size 53622996
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16e192b0589cb76aab58b5f5ff6b1a79c987a5044492d36eb1539979e1cae814
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7b07705cdd965f3a6be3f96556df5291ffbacca044c445cd4e4aab2e1bcb8ff
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.005463236967903483,
5
  "eval_steps": 3,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 26.027,
74
  "eval_steps_per_second": 13.041,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1882395078819840.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.008194855451855224,
5
  "eval_steps": 3,
6
+ "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 26.027,
74
  "eval_steps_per_second": 13.041,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.006373776462554063,
79
+ "grad_norm": 1.7010599374771118,
80
+ "learning_rate": 0.00014,
81
+ "loss": 5.1033,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.007284315957204644,
86
+ "grad_norm": 1.974336862564087,
87
+ "learning_rate": 0.00016,
88
+ "loss": 4.5382,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.008194855451855224,
93
+ "grad_norm": 2.7550885677337646,
94
+ "learning_rate": 0.00018,
95
+ "loss": 7.4902,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.008194855451855224,
100
+ "eval_loss": 1.5171022415161133,
101
+ "eval_runtime": 17.7942,
102
+ "eval_samples_per_second": 26.02,
103
+ "eval_steps_per_second": 13.038,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2823592618229760.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null